FilesExpand file tree

 main

/

test_udf.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

126 lines (94 loc) · 3.5 KB

 main

/

test_udf.py

Copy path

Top

File metadata and controls

• Code
• Blame

126 lines (94 loc) · 3.5 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

# Licensed to the Apache Software Foundation (ASF) under one

# or more contributor license agreements. See the NOTICE file

# distributed with this work for additional information

# regarding copyright ownership. The ASF licenses this file

# to you under the Apache License, Version 2.0 (the

# "License"); you may not use this file except in compliance

# with the License. You may obtain a copy of the License at

#

# http://www.apache.org/licenses/LICENSE-2.0

#

# Unless required by applicable law or agreed to in writing,

# software distributed under the License is distributed on an

# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY

# KIND, either express or implied. See the License for the

# specific language governing permissions and limitations

# under the License.

import pyarrow as pa

import pytest

from datafusion import column, udf

@pytest.fixture

def df(ctx):

# create a RecordBatch and a new DataFrame from it

batch = pa.RecordBatch.from_arrays(

[pa.array([1, 2, 3]), pa.array([4, 4, None])],

names=["a", "b"],

)

return ctx.create_dataframe([[batch]], name="test_table")

def test_udf(df):

# is_null is a pa function over arrays

is_null = udf(

lambda x: x.is_null(),

[pa.int64()],

pa.bool_(),

volatility="immutable",

)

df = df.select(is_null(column("b")))

result = df.collect()[0].column(0)

assert result == pa.array([False, False, True])

def test_udf_decorator(df):

@udf([pa.int64()], pa.bool_(), "immutable")

def is_null(x: pa.Array) -> pa.Array:

return x.is_null()

df = df.select(is_null(column("b")))

result = df.collect()[0].column(0)

assert result == pa.array([False, False, True])

def test_register_udf(ctx, df) -> None:

is_null = udf(

lambda x: x.is_null(),

[pa.float64()],

pa.bool_(),

volatility="immutable",

name="is_null",

)

ctx.register_udf(is_null)

df_result = ctx.sql("select is_null(b) from test_table")

result = df_result.collect()[0].column(0)

assert result == pa.array([False, False, True])

class OverThresholdUDF:

def __init__(self, threshold: int = 0) -> None:

self.threshold = threshold

def __call__(self, values: pa.Array) -> pa.Array:

return pa.array(v.as_py() >= self.threshold for v in values)

def test_udf_with_parameters_function(df) -> None:

udf_no_param = udf(

OverThresholdUDF(),

pa.int64(),

pa.bool_(),

volatility="immutable",

)

df1 = df.select(udf_no_param(column("a")))

result = df1.collect()[0].column(0)

assert result == pa.array([True, True, True])

udf_with_param = udf(

OverThresholdUDF(2),

pa.int64(),

pa.bool_(),

volatility="immutable",

)

df2 = df.select(udf_with_param(column("a")))

result = df2.collect()[0].column(0)

assert result == pa.array([False, True, True])

def test_udf_with_parameters_decorator(df) -> None:

@udf([pa.int64()], pa.bool_(), "immutable")

def udf_no_param(values: pa.Array) -> pa.Array:

return OverThresholdUDF()(values)

df1 = df.select(udf_no_param(column("a")))

result = df1.collect()[0].column(0)

assert result == pa.array([True, True, True])

@udf([pa.int64()], pa.bool_(), "immutable")

def udf_with_param(values: pa.Array) -> pa.Array:

return OverThresholdUDF(2)(values)

df2 = df.select(udf_with_param(column("a")))

result = df2.collect()[0].column(0)

assert result == pa.array([False, True, True])